github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14443] success to create qwen 3.5 q8 in GGUF, but fail to run #55893

New Issue
Closed
opened 2026-04-29 09:54:20 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-29 09:54:20 -05:00
Owner
Copy Link

Originally created by @taozhiyuai on GitHub (Feb 26, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14443

What is the issue?

taozhiyu@Mac ~ % ollama list
NAME                           ID              SIZE     MODIFIED           
qwen35-35b-a3b:q8_0            40c3699330db    36 GB    About a minute ago 

taozhiyu@Mac ~ % ollama run qwen35-35b-a3b:q8_0
Error: 500 Internal Server Error: unable to load model: /Users/taozhiyu/.ollama/models/blobs/sha256-42fcd4b5080b3db03410736f1339dfdf491afacf859df83b4cc8ae1faea48a7f

taozhiyu@Mac ~ % ollama --version
ollama version is 0.17.1-rc2

taozhiyu@TAOZHIYUs-MacBook-Pro ~ % ollama run qwen35-35b-a3b:q8_0 Error: 500 Internal Server Error: unable to load model: /Users/taozhiyu/.ollama/models/blobs/sha256-42fcd4b5080b3db03410736f1339dfdf491afacf859df83b4cc8ae1faea48a7f taozhiyu@TAOZHIYUs-MacBook-Pro ~ % ollama --version ollama version is 0.17.4

Relevant log output

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.17.1-rc2

Originally created by @taozhiyuai on GitHub (Feb 26, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14443 ### What is the issue? ``` taozhiyu@Mac ~ % ollama list NAME ID SIZE MODIFIED qwen35-35b-a3b:q8_0 40c3699330db 36 GB About a minute ago taozhiyu@Mac ~ % ollama run qwen35-35b-a3b:q8_0 Error: 500 Internal Server Error: unable to load model: /Users/taozhiyu/.ollama/models/blobs/sha256-42fcd4b5080b3db03410736f1339dfdf491afacf859df83b4cc8ae1faea48a7f taozhiyu@Mac ~ % ollama --version ollama version is 0.17.1-rc2 ``` `taozhiyu@TAOZHIYUs-MacBook-Pro ~ % ollama run qwen35-35b-a3b:q8_0 Error: 500 Internal Server Error: unable to load model: /Users/taozhiyu/.ollama/models/blobs/sha256-42fcd4b5080b3db03410736f1339dfdf491afacf859df83b4cc8ae1faea48a7f taozhiyu@TAOZHIYUs-MacBook-Pro ~ % ollama --version ollama version is 0.17.4` ### Relevant log output ```shell ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.17.1-rc2
GiteaMirror added the bug label 2026-04-29 09:54:20 -05:00
GiteaMirror commented 2026-04-29 09:54:22 -05:00
Author
Owner
Copy Link

@chidugit commented on GitHub (Feb 26, 2026):

Same issue here!

<!-- gh-comment-id:3967359313 --> @chidugit commented on GitHub (Feb 26, 2026): Same issue here!
GiteaMirror commented 2026-04-29 09:54:22 -05:00
Author
Owner
Copy Link

@battmanux commented on GitHub (Feb 26, 2026):

Same here on Linux Ubuntu 24.04. RTX5090. (Ollama server logs : qwen35 not supported / qwen35moe not supported)

<!-- gh-comment-id:3967458593 --> @battmanux commented on GitHub (Feb 26, 2026): Same here on Linux Ubuntu 24.04. RTX5090. (Ollama server logs : qwen35 not supported / qwen35moe not supported)
GiteaMirror commented 2026-04-29 09:54:23 -05:00
Author
Owner
Copy Link

@kerta1n commented on GitHub (Feb 27, 2026):

Same here on Debian Trixie, RTX3090 with the model hf.co/unsloth/Qwen3.5-27B-GGUF:Q8_0

<!-- gh-comment-id:3970528039 --> @kerta1n commented on GitHub (Feb 27, 2026): Same here on Debian Trixie, RTX3090 with the model `hf.co/unsloth/Qwen3.5-27B-GGUF:Q8_0`
GiteaMirror commented 2026-04-29 09:54:23 -05:00
Author
Owner
Copy Link

@ka-admin commented on GitHub (Feb 27, 2026):

Feb 27 09:59:02 ollama[1985]: llama_model_loader: - type q8_0: 518 tensors
Feb 27 09:59:02 ollama[1985]: print_info: file format = GGUF V3 (latest)
Feb 27 09:59:02 ollama[1985]: print_info: file type = Q8_0
Feb 27 09:59:02 ollama[1985]: print_info: file size = 120.94 GiB (8.51 BPW)
Feb 27 09:59:02 ollama[1985]: llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35moe'
Feb 27 09:59:02 ollama[1985]: llama_model_load_from_file_impl: failed to load model

Ollama 0.17.4

<!-- gh-comment-id:3971214684 --> @ka-admin commented on GitHub (Feb 27, 2026): Feb 27 09:59:02 ollama[1985]: llama_model_loader: - type q8_0: 518 tensors Feb 27 09:59:02 ollama[1985]: print_info: file format = GGUF V3 (latest) Feb 27 09:59:02 ollama[1985]: print_info: file type = Q8_0 Feb 27 09:59:02 ollama[1985]: print_info: file size = 120.94 GiB (8.51 BPW) Feb 27 09:59:02 ollama[1985]: llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35moe' Feb 27 09:59:02 ollama[1985]: llama_model_load_from_file_impl: failed to load model Ollama 0.17.4
GiteaMirror commented 2026-04-29 09:54:24 -05:00
Author
Owner
Copy Link

@GitUsers1234 commented on GitHub (Feb 27, 2026):

same issue with Ollama 0.17.4 even though it claims to support. Quite confusing.

<!-- gh-comment-id:3971273033 --> @GitUsers1234 commented on GitHub (Feb 27, 2026): same issue with Ollama 0.17.4 even though it claims to support. Quite confusing.
GiteaMirror commented 2026-04-29 09:54:24 -05:00
Author
Owner
Copy Link

@iWangJiaxiang commented on GitHub (Feb 27, 2026):

Feb 27 09:59:02 ollama[1985]: llama_model_loader: - type q8_0: 518 tensors Feb 27 09:59:02 ollama[1985]: print_info: file format = GGUF V3 (latest) Feb 27 09:59:02 ollama[1985]: print_info: file type = Q8_0 Feb 27 09:59:02 ollama[1985]: print_info: file size = 120.94 GiB (8.51 BPW) Feb 27 09:59:02 ollama[1985]: llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35moe' Feb 27 09:59:02 ollama[1985]: llama_model_load_from_file_impl: failed to load model

Ollama 0.17.4

Same issue when using model from huggingface

<!-- gh-comment-id:3971331321 --> @iWangJiaxiang commented on GitHub (Feb 27, 2026): > Feb 27 09:59:02 ollama[1985]: llama_model_loader: - type q8_0: 518 tensors Feb 27 09:59:02 ollama[1985]: print_info: file format = GGUF V3 (latest) Feb 27 09:59:02 ollama[1985]: print_info: file type = Q8_0 Feb 27 09:59:02 ollama[1985]: print_info: file size = 120.94 GiB (8.51 BPW) Feb 27 09:59:02 ollama[1985]: llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35moe' Feb 27 09:59:02 ollama[1985]: llama_model_load_from_file_impl: failed to load model > > Ollama 0.17.4 Same issue when using model from huggingface
GiteaMirror commented 2026-04-29 09:54:24 -05:00
Author
Owner
Copy Link

@YJesus commented on GitHub (Feb 27, 2026):

https://github.com/ollama/ollama/issues/14419#issuecomment-3959159035

<!-- gh-comment-id:3972337948 --> @YJesus commented on GitHub (Feb 27, 2026): https://github.com/ollama/ollama/issues/14419#issuecomment-3959159035
GiteaMirror commented 2026-04-29 09:54:25 -05:00
Author
Owner
Copy Link

@tgiraud2007 commented on GitHub (Feb 27, 2026):

Same here

<!-- gh-comment-id:3972987267 --> @tgiraud2007 commented on GitHub (Feb 27, 2026): Same here
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#55893
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?